problem-framing

An open-source Agent Skill for problem framing and assumption testing across coding, debugging, architecture, scientific research, and product decisions.

认知视角检查器｜以减少用户与 AI 的认知窄化为目标，服务早期项目、设计与决策。少量关键补问理解背景与规则，检验双方预设，对照实质不同的视角、证据与取舍，给出条件建议，由用户选择是否验证、推演或制作方案。Agent Skill for critical thinking and decision support: check assumptions, compare perspectives. Copilot / Codex.

Cursor skills and harness-oriented workflows for project intake, problem framing, and AI-ready task decomposition.

Free Agent Skills that pressure-test AI project ideas and diagnose running systems. From the AI Problem Framing course.

A well-defined problem comes FIRST. A problem-definition skill that interrogates until the problem is sharp, pins the constraints that channel creativity, and hunts the web for evidence of how others framed and solved it.

Local CLI that runs a problem through company, team, culture, strategy, roadmap, technical, operational, financial, and user lenses and writes the notes to disk.

Aperture Lite — frame the right problem before you build the AI. A public, lightweight version of Michael Joseph's Aperture method.

Focus Field: an executable orientation layer for locating the field, deriving the governing question, and keeping the next move valid.

AI systems with a focus on NLP: retrieval‑augmented generation (RAG), agentic workflows, evaluation harnesses, and production patterns. This repo is the entry point to my portfolio.

Open research: first test whether energy density is the right problem. Review assumptions, compare alternatives, and reuse AI-readable records.